Triple

T15521468
Position Surface form Disambiguated ID Type / Status
Subject Kristalina Georgieva E368977 entity
Predicate givenName P17 FINISHED
Object Kristalina E368977 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kristalina | Statement: [Kristalina Georgieva, givenName, Kristalina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kristalina
Context triple: [Kristalina Georgieva, givenName, Kristalina]
  • A. Kristalina chosen
    Kristalina is the first name of Kristalina Georgieva, a Bulgarian economist and the Managing Director of the International Monetary Fund.
  • B. Maria Kanova
    Maria Kanova was the wife of German novelist Heinrich Mann, associated with his later life and exile period.
  • C. Katherine Tsina
    Katherine Tsina is an American artist and designer best known as the wife of musician Andrew Bird and for her work in visual arts and fashion.
  • D. Kristina
    Kristina is a feminine given name commonly used in various European countries, often considered a variant of Christina.
  • E. Ekaterina Gradova
    Ekaterina Gradova was a Soviet and Russian actress best known for her roles in popular 1970s film and television productions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d85a1794cc8190b0b428716296e63e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0403543188190abac49d2b9decb89 completed April 16, 2026, 1:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d54ea5c8190b3b220ad10ba8f40 completed May 9, 2026, 1:57 p.m.
Created at: April 10, 2026, 4:04 a.m.